FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950152428> ?p ?o ?g. }

• W2950152428 abstract "Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric information game with no such model or interaction. Our approach is to encourage an agent to reveal or hide their intentions using an information-theoretic regularizer. We consider both the mutual information between goal and action given state, as well as the mutual information between goal and state. We show how to optimize these regularizers in a way that is easy to integrate with policy gradient reinforcement learning. Finally, we demonstrate that cooperative (competitive) policies learned with our approach lead to more (less) reward for a second agent in two simple asymmetric information games." @default.
• W2950152428 created "2019-06-27" @default.
• W2950152428 creator A5024625209 @default.
• W2950152428 creator A5047843932 @default.
• W2950152428 creator A5060296717 @default.
• W2950152428 creator A5083742002 @default.
• W2950152428 creator A5089226694 @default.
• W2950152428 date "2018-08-06" @default.
• W2950152428 modified "2023-09-27" @default.
• W2950152428 title "Learning to Share and Hide Intentions using Information Regularization" @default.
• W2950152428 cites W1519783625 @default.
• W2950152428 cites W1542941925 @default.
• W2950152428 cites W1992154343 @default.
• W2950152428 cites W1999874108 @default.
• W2950152428 cites W2061562262 @default.
• W2950152428 cites W2106980598 @default.
• W2950152428 cites W2134906087 @default.
• W2950152428 cites W2148886952 @default.
• W2950152428 cites W2151516755 @default.
• W2950152428 cites W2155027007 @default.
• W2950152428 cites W2157331557 @default.
• W2950152428 cites W2551887912 @default.
• W2950152428 cites W2557026499 @default.
• W2950152428 cites W2787542351 @default.
• W2950152428 cites W2891661335 @default.
• W2950152428 cites W2895921264 @default.
• W2950152428 cites W2962940757 @default.
• W2950152428 cites W2963160877 @default.
• W2950152428 cites W2963162637 @default.
• W2950152428 cites W2963199420 @default.
• W2950152428 cites W2963276097 @default.
• W2950152428 cites W2963289505 @default.
• W2950152428 cites W2963438456 @default.
• W2950152428 cites W2963627051 @default.
• W2950152428 cites W2964043796 @default.
• W2950152428 cites W2964345382 @default.
• W2950152428 cites W3123377635 @default.
• W2950152428 hasPublicationYear "2018" @default.
• W2950152428 type Work @default.
• W2950152428 sameAs 2950152428 @default.
• W2950152428 citedByCount "3" @default.
• W2950152428 countsByYear W29501524282018 @default.
• W2950152428 countsByYear W29501524282020 @default.
• W2950152428 countsByYear W29501524282021 @default.
• W2950152428 crossrefType "posted-content" @default.
• W2950152428 hasAuthorship W2950152428A5024625209 @default.
• W2950152428 hasAuthorship W2950152428A5047843932 @default.
• W2950152428 hasAuthorship W2950152428A5060296717 @default.
• W2950152428 hasAuthorship W2950152428A5083742002 @default.
• W2950152428 hasAuthorship W2950152428A5089226694 @default.
• W2950152428 hasConcept C121332964 @default.
• W2950152428 hasConcept C152139883 @default.
• W2950152428 hasConcept C154945302 @default.
• W2950152428 hasConcept C18903297 @default.
• W2950152428 hasConcept C26517878 @default.
• W2950152428 hasConcept C2776135515 @default.
• W2950152428 hasConcept C2780791683 @default.
• W2950152428 hasConcept C38652104 @default.
• W2950152428 hasConcept C41008148 @default.
• W2950152428 hasConcept C62520636 @default.
• W2950152428 hasConcept C86803240 @default.
• W2950152428 hasConcept C91306197 @default.
• W2950152428 hasConcept C97541855 @default.
• W2950152428 hasConceptScore W2950152428C121332964 @default.
• W2950152428 hasConceptScore W2950152428C152139883 @default.
• W2950152428 hasConceptScore W2950152428C154945302 @default.
• W2950152428 hasConceptScore W2950152428C18903297 @default.
• W2950152428 hasConceptScore W2950152428C26517878 @default.
• W2950152428 hasConceptScore W2950152428C2776135515 @default.
• W2950152428 hasConceptScore W2950152428C2780791683 @default.
• W2950152428 hasConceptScore W2950152428C38652104 @default.
• W2950152428 hasConceptScore W2950152428C41008148 @default.
• W2950152428 hasConceptScore W2950152428C62520636 @default.
• W2950152428 hasConceptScore W2950152428C86803240 @default.
• W2950152428 hasConceptScore W2950152428C91306197 @default.
• W2950152428 hasConceptScore W2950152428C97541855 @default.
• W2950152428 hasLocation W29501524281 @default.
• W2950152428 hasOpenAccess W2950152428 @default.
• W2950152428 hasPrimaryLocation W29501524281 @default.
• W2950152428 hasRelatedWork W1630986973 @default.
• W2950152428 hasRelatedWork W2137377401 @default.
• W2950152428 hasRelatedWork W2292545284 @default.
• W2950152428 hasRelatedWork W2407638781 @default.
• W2950152428 hasRelatedWork W2594794854 @default.
• W2950152428 hasRelatedWork W2754718400 @default.
• W2950152428 hasRelatedWork W2806219019 @default.
• W2950152428 hasRelatedWork W2808210333 @default.
• W2950152428 hasRelatedWork W2886000153 @default.
• W2950152428 hasRelatedWork W2893175095 @default.
• W2950152428 hasRelatedWork W2959402823 @default.
• W2950152428 hasRelatedWork W3045017927 @default.
• W2950152428 hasRelatedWork W3113310958 @default.
• W2950152428 hasRelatedWork W3124222680 @default.
• W2950152428 hasRelatedWork W3132138270 @default.
• W2950152428 hasRelatedWork W3169581295 @default.
• W2950152428 hasRelatedWork W3210631127 @default.
• W2950152428 hasRelatedWork W98046558 @default.
• W2950152428 hasRelatedWork W2185790752 @default.
• W2950152428 hasRelatedWork W3092868385 @default.
• W2950152428 isParatext "false" @default.

• next